Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3685 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0925. Min Range: -6.0925
Max Act: 6.0925. Min Act: -0.1700
Data Index: 8480619 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.6237. Min Act: -0.1700
Data Index: 8104951 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.6237. Min Act: -0.1700
Data Index: 4988009 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.4050. Min Act: -0.1700
Data Index: 664043 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.4050. Min Act: -0.1700
Data Index: 5121748 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.3425. Min Act: -0.1700
Data Index: 7671435 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.3112. Min Act: -0.1700
Data Index: 2150111 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.3112. Min Act: -0.1700
Data Index: 2391002 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.3112. Min Act: -0.1700
Data Index: 2592739 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.3112. Min Act: -0.1700
Data Index: 8577049 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.3112. Min Act: -0.1700
Data Index: 258471 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.2800. Min Act: -0.1700
Data Index: 6815590 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.2487. Min Act: -0.1700
Data Index: 5152728 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.2487. Min Act: -0.1700
Data Index: 7218739 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.2487. Min Act: -0.1700
Data Index: 3328409 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.2175. Min Act: -0.1700
Data Index: 412146 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.2175. Min Act: -0.1700
Data Index: 5858021 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.2175. Min Act: -0.1700
Data Index: 6812259 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.2175. Min Act: -0.1700
Data Index: 296608 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0925. Min Range: -6.0925
Max Act: 5.1862. Min Act: -0.1700
Data Index: 4676011 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19